[Patch RFC 11/13] vt-d: If the Device-TLB flush is still not completed when

[Quan Xu <quan.xu@intel.com>]

to destroy virtual machine, schedule and wait on a waitqueue
until the Device-TLB flush is completed.

Signed-off-by: Quan Xu <quan.xu@intel.com>
---
 xen/common/domain.c                 | 10 ++++++++++
 xen/drivers/passthrough/vtd/iommu.c |  9 +++++++++
 xen/include/xen/hvm/iommu.h         |  6 ++++++
 3 files changed, 25 insertions(+)

diff --git a/xen/common/domain.c b/xen/common/domain.c
index 1f62e3b..8ccc1a5 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -867,6 +867,16 @@ void domain_destroy(struct domain *d)
     rcu_assign_pointer(*pd, d->next_in_hashbucket);
     spin_unlock(&domlist_update_lock);
 
+#ifdef HAS_PASSTHROUGH
+    /*
+     * If the Device-TLB flush is still not completed, schedule
+     * and wait on a waitqueue until the Device-TLB flush is
+     * completed.
+     */
+    if ( need_iommu(d) && QI_FLUSHING(d) )
+        wait_for_qi_flushing(d);
+#endif
+
     /* Schedule RCU asynchronous completion of domain destroy. */
     call_rcu(&d->rcu, complete_domain_destroy);
 }
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 1297dea..3d98fea 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1070,6 +1070,11 @@ static hw_irq_controller dma_msi_type = {
 };
 
 /* IOMMU Queued Invalidation(QI). */
+void wait_for_qi_flushing(struct domain *d)
+{
+    wait_event(qi_wq(d), !QI_FLUSHING(d));
+}
+
 static void qi_clear_iwc(struct iommu *iommu)
 {
     unsigned long flags;
@@ -1188,6 +1193,7 @@ scan_again:
                 }
                 spin_unlock(&qi_page_lock(d));
                 QI_FLUSHING(d) = 0;
+                wake_up_all(&qi_wq(d));
             }
             rcu_unlock_domain(d);
         }
@@ -1494,6 +1500,7 @@ static int intel_iommu_domain_init(struct domain *d)
     hd->arch.agaw = width_to_agaw(DEFAULT_DOMAIN_ADDRESS_WIDTH);
     INIT_PAGE_LIST_HEAD(&qi_hold_page_list(d));
     spin_lock_init(&qi_page_lock(d));
+    init_waitqueue_head(&qi_wq(d));
 
     return 0;
 }
@@ -1925,6 +1932,8 @@ static void iommu_domain_teardown(struct domain *d)
     if ( list_empty(&acpi_drhd_units) )
         return;
 
+    destroy_waitqueue_head(&qi_wq(d));
+
     list_for_each_entry_safe ( mrmrr, tmp, &hd->arch.mapped_rmrrs, list )
     {
         list_del(&mrmrr->list);
diff --git a/xen/include/xen/hvm/iommu.h b/xen/include/xen/hvm/iommu.h
index 5dc0033..f661c8c 100644
--- a/xen/include/xen/hvm/iommu.h
+++ b/xen/include/xen/hvm/iommu.h
@@ -20,6 +20,7 @@
 #define __XEN_HVM_IOMMU_H__
 
 #include <xen/iommu.h>
+#include <xen/wait.h>
 #include <xen/list.h>
 #include <asm/hvm/iommu.h>
 
@@ -56,12 +57,15 @@ struct hvm_iommu {
     struct page_list_head qi_hold_page_list;
     spinlock_t qi_lock;
 
+    struct waitqueue_head qi_wq;
+
     /* Features supported by the IOMMU */
     DECLARE_BITMAP(features, IOMMU_FEAT_count);
 };
 
 void do_qi_flushing(struct domain *d);
 void qi_hold_page(struct domain *d, struct page_info *pg);
+void wait_for_qi_flushing(struct domain *d);
 
 #define iommu_set_feature(d, f)   set_bit((f), domain_hvm_iommu(d)->features)
 #define iommu_clear_feature(d, f) clear_bit((f), domain_hvm_iommu(d)->features)
@@ -76,5 +80,7 @@ void qi_hold_page(struct domain *d, struct page_info *pg);
     (d->arch.hvm_domain.hvm_iommu.qi_hold_page_list)
 #define qi_page_lock(d) \
     (d->arch.hvm_domain.hvm_iommu.qi_lock)
+#define qi_wq(d) \
+    (d->arch.hvm_domain.hvm_iommu.qi_wq)
 
 #endif /* __XEN_HVM_IOMMU_H__ */
-- 
1.8.3.2